SpaceMeshLab：空间上下文记忆和网格Atrous卷积共识的语义分割
SpaceMeshLab: Spatial Context Memoization and Meshgrid Atrous Convolution Consensus for Semantic Segmentation
摘要：
语义分割网络采用了图像分类网络的迁移学习方法，该方法存在空间上下文信息不足的问题。出于这个原因，我们提出了空间上下文记忆（SpaM），一个旁路分支的空间上下文，通过保留输入的尺寸和不断沟通的空间上下文和丰富的语义信息相互骨干网络。语义分割的多尺度上下文信息对于处理给定场景中不同大小和形状的目标对象至关重要。传统的多尺度上下文方法通过多次膨胀率或池化操作来获得多个有效感受野，但往往存在相对于目标像素的失准问题。为此，我们提出了Meshgrid Atrous Convolution Consensus（MetroCon^2），它使用具有网格状分散膨胀率的卷积将多尺度方案带入细粒度多尺度对象上下文。SpaceMeshLab（ResNet-101 + SpaM + MetroCon^2）在Cityscapes测试中实现了82.0%的mIoU，在Pascal-Context验证集上实现了53.5%的mIoU。
英文摘要：
Semantic segmentation networks adopt transfer learning from image classification networks which occurs a shortage of spatial context information. For this reason, we propose Spatial Context Memoization (SpaM), a bypassing branch for spatial context by retaining the input dimension and constantly communicating its spatial context and rich semantic information mutually with the backbone network. Multi-scale context information for semantic segmentation is crucial for dealing with diverse sizes and shapes of target objects in the given scene. Conventional multi-scale context scheme adopts multiple effective receptive fields by multiple dilation rates or pooling operations, but often suffer from misalignment problem with respect to the target pixel. To this end, we propose Meshgrid Atrous Convolution Consensus (MetroCon^2) which brings multi-scale scheme into fine-grained multi-scale object context using convolutions with meshgrid-like scattered dilation rates. SpaceMeshLab (ResNet-101 + SpaM + MetroCon^2) achieves 82.0% mIoU in Cityscapes test and 53.5% mIoU on Pascal-Context validation set.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
